main.py

from langchain.schema import AIMessage, HumanMessage
import gradio as gr
from langchain_community.llms import Ollama

llm = Ollama(model="llama3:8b", timeout=1000)

def predict(message, history):
    history_langchain_format = []
    for human, ai in history:
        history_langchain_format.append(HumanMessage(content=human))
        history_langchain_format.append(AIMessage(content=ai))
    history_langchain_format.append(HumanMessage(content=message))
    try:
        chat_response = llm.invoke(history_langchain_format)
    except chat_response as e:
        chat_response = "Error: " + str(e)
        
    return chat_response

def run():
    demo = gr.ChatInterface(predict)
    demo.launch(server_name="0.0.0.0", server_port=7860)


if __name__ == "__main__":
    run()